Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4823 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1109043 (The Pile)

Max Activating Token Index: 1007

Text #1

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.2475. Min Act: -0.0000

Data Index: 1905780 (The Pile)

Max Activating Token Index: 459

Text #2

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.2543. Min Act: -0.0000

Data Index: 746779 (The Pile)

Max Activating Token Index: 219

Text #3

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.2805. Min Act: -0.0000

Data Index: 44214 (The Pile)

Max Activating Token Index: 643

Text #4

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1436. Min Act: -0.0000

Data Index: 899967 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1900. Min Act: -0.0000

Data Index: 1011126 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.2169. Min Act: -0.0000

Data Index: 785689 (The Pile)

Max Activating Token Index: 304

Text #7

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1435677 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1668. Min Act: -0.0000

Data Index: 435320 (The Pile)

Max Activating Token Index: 249

Text #9

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.2142. Min Act: -0.0000

Data Index: 330606 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1056. Min Act: -0.0000

Data Index: 557725 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1234. Min Act: -0.0000

Data Index: 341378 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1032. Min Act: -0.0000

Data Index: 1758803 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1008. Min Act: -0.0000

Data Index: 1131817 (The Pile)

Max Activating Token Index: 649

Text #14

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0484. Min Act: -0.0000

Data Index: 570258 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1465. Min Act: -0.0000

Data Index: 316950 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1926. Min Act: -0.0000

Data Index: 1697733 (The Pile)

Max Activating Token Index: 871

Text #17

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1252771 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0153. Min Act: -0.0000

Data Index: 423124 (The Pile)

Max Activating Token Index: 210

Text #19

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0934. Min Act: -0.0000

Data Index: 687072 (The Pile)

Max Activating Token Index: 790